Reliable automatic seizure detection from long-term EEG remains a challenge, as current machine learning models often fail to generalize across patients or clinical settings. Manual EEG review remains the clinical standard, underscoring the need for robust models and standardized evaluation. To rigorously assess algorithm performance, we organized a challenge using a private dataset of continuous EEG recordings from 65 subjects (4,360 hours). Expert neurophysiologists annotated the data, providing ground truth for seizure events. Participants were required to detect seizure onset and duration, with evaluation based on event-based metrics, including sensitivity, precision, F1-score, and false positives per day. The SzCORE framework ensured standardized evaluation. The primary ranking criterion was the event-based F1-score, reflecting clinical relevance by balancing sensitivity and false positives. The challenge received 30 submissions from 19 teams, with 28 algorithms evaluated. Results revealed wide variability in performance, with a top F1-score of 43% (sensitivity 37%, precision 45%), highlighting the ongoing difficulty of seizure detection. The challenge also revealed a gap between reported performance and real-world evaluation, emphasizing the importance of rigorous benchmarking. Compared to previous challenges and commercial systems, the best-performing algorithm in this contest showed improved performance. Importantly, the challenge platform now supports continuous benchmarking, enabling reproducible research, integration of new datasets, and clinical evaluation of seizure detection algorithms using a standardized framework.

Generating synthetic ECG data has numerous applications in healthcare, from educational purposes to simulating scenarios and forecasting trends. While recent diffusion models excel at generating short ECG segments, they struggle with longer sequences needed for many clinical applications. This paper proposes a novel three-layer synthesis framework for generating realistic long-form ECG signals. We first generate high-fidelity single beats using a diffusion model, then synthesize inter-beat features preserving critical temporal dependencies, and finally assemble beats into coherent long sequences using feature-guided matching. Our comprehensive evaluation demonstrates that the resulting synthetic ECGs maintain both beat-level morphological fidelity and clinically relevant inter-beat relationships. In arrhythmia classification tasks, our long-form synthetic ECGs significantly outperform end-to-end long-form ECG generation using the diffusion model, highlighting their potential for increasing utility for downstream applications. The approach enables generation of unprecedented multi-minute ECG sequences while preserving essential diagnostic characteristics.

Understanding and predicting human emotional and physiological states using wearable sensors has critical applications in stress monitoring, mental health assessment, and affective computing. In this study, we present a novel Multi - Task Physics - Informed Neural Network (PINN) that simultaneously performs Electrodermal Activity (EDA) prediction and emotion classification using the publicly available WESAD dataset. Our model integrates psychological self - reports (PANAS and SAM) with a physics - inspired differential formulation of EDA dynamics, enforcing biophysically grounded constraints through a custom loss that balances data - driven learning and physiological interpretability. The architecture supports dual outputs -- regression for EDA and classification for emotional states -- trained under a unified multi - task framework. Evaluated via 5 - fold cross - validation, the proposed method achieves an average EDA RMSE of 0.0362, Pearson correlation (r) of 0.9919, and F1 - score of 94.08%, outperforming both classical baselines (e.g., SVR, XGBoost) and ablated variants such as emotion - only and EDA - only models. Comparative ablation and multi - task experiments show that including both physics constraints and emotion prediction enhances generalization, reduces overfitting, and leads to physiologically consistent outputs. Moreover, the learned physical parameters -- decay rate (α), emotion influence weights (β), and temporal scaling (γ) -- remain interpretable and stable across folds, confirming the alignment between the model's latent representation and known stress - response theory. This is the first work to introduce a multi - task PINN architecture for wearable affective computing, bridging black - box deep learning and domain knowledge. Our framework lays the groundwork for interpretable, multimodal, and deployable systems in healthcare and human - computer interaction.

The sample covariance matrix is a cornerstone of multivariate statistics, but it is highly sensitive to outliers. These can be casewise outliers, such as cases belonging to a different population, or cellwise outliers, which are deviating cells (entries) of the data matrix. Recently some robust covariance estimators have been developed that can handle both types of outliers, but their computation is only feasible up to at most 20 dimensions. To remedy this we propose the cellRCov method, a robust covariance estimator that simultaneously handles casewise outliers, cellwise outliers, and missing data. It relies on a decomposition of the covariance on principal and orthogonal subspaces, leveraging recent work on robust PCA. It also employs a ridge-type regularization to stabilize the estimated covariance matrix. We establish some theoretical properties of cellRCov, including its casewise and cellwise influence functions as well as consistency and asymptotic normality. A simulation study demonstrates the superior performance of cellRCov in contaminated and missing data scenarios. Furthermore, its practical utility is illustrated in a real-world application to anomaly detection. We also construct and illustrate the cellRCCA method for robust and regularized canonical correlation analysis.

Watermarking images is critical for tracking image provenance and proving ownership. With the advent of generative models, such as stable diffusion, that can create fake but realistic images, watermarking has become particularly important to make human-created images reliably identifiable. Unfortunately, the very same stable diffusion technology can remove watermarks injected using existing methods.To address this problem, we present ZoDiac, which uses a pre-trained stable diffusion model to inject a watermark into the trainable latent space, resulting in watermarks that can be reliably detected in the latent vector even when attacked. We evaluate ZoDiac on three benchmarks, MS-COCO, DiffusionDB, and WikiArt, and find that ZoDiac is robust against state-of-the-art watermark attacks, with a watermark detection rate above 98% and a false positive rate below 6.4%, outperforming state-of-the-art watermarking methods. We hypothesize that the reciprocating denoising process in diffusion models may inherently enhance the robustness of the watermark when faced with strong attacks and validate the hypothesis.

Large Language Models (LLMs) are typically trained to predict in the forward direction of time. However, recent works have shown that prompting these models to look back and critique their own generations can produce useful feedback. Motivated by this, we explore the question of whether LLMs can be empowered to think (predict and score) backwards to provide unsupervised feedback that complements forward LLMs. Towards this, we introduce Time Reversed Language Models (TRLMs), which can score and generate queries when conditioned on responses, effectively functioning in the reverse direction of time. We show empirically (and theoretically in a stylized setting) that time-reversed models can indeed complement forward model predictions when used to score the query given response for re-ranking multiple forward generations.

This paper conducts a comprehensive study of the learning curves of kernel ridge regression (KRR) under minimal assumptions.Our contributions are three-fold: 1) we analyze the role of key properties of the kernel, such as its spectral eigen-decay, the characteristics of the eigenfunctions, and the smoothness of the kernel; 2) we demonstrate the validity of the Gaussian Equivalent Property (GEP), which states that the generalization performance of KRR remains the same when the whitened features are replaced by standard Gaussian vectors, thereby shedding light on the success of previous analyzes under the Gaussian Design Assumption; 3) we derive novel bounds that improve over existing bounds across a broad range of setting such as (in)dependent feature vectors and various combinations of eigen-decay rates in the over/underparameterized regimes.

Backdoor attack is a common threat to deep neural networks. During testing, samples embedded with a backdoor trigger will be misclassified as an adversarial target by a backdoored model, while samples without the backdoor trigger will be correctly classified. In this paper, we present the first certified backdoor detector (CBD), which is based on a novel, adjustable conformal prediction scheme based on our proposed statistic local dominant probability. For any classifier under inspection, CBD provides 1) a detection inference, 2) the condition under which the attacks are guaranteed to be detectable for the same classification domain, and 3) a probabilistic upper bound for the false positive rate. Our theoretical results show that attacks with triggers that are more resilient to test-time noise and have smaller perturbation magnitudes are more likely to be detected with guarantees.

Current PAC-Bayes generalisation bounds are restricted to scalar metrics of performance, such as the loss or error rate. However, one ideally wants more information-rich certificates that control the entire distribution of possible outcomes, such as the distribution of the test loss in regression, or the probabilities of different mis-classifications. We provide the first PAC-Bayes bound capable of providing such rich information by bounding the Kullback-Leibler divergence between the empirical and true probabilities of a set of M error types, which can either be discretized loss values for regression, or the elements of the confusion matrix (or a partition thereof) for classification. We transform our bound into a differentiable training objective. Our bound is especially useful in cases where the severity of different mis-classifications may change over time; existing PAC-Bayes bounds can only bound a particular pre-decided weighting of the error types. In contrast our bound implicitly controls all uncountably many weightings simultaneously.

Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factuality" of claims decomposed from a language model generation and applying conformal prediction techniques to filter out those claims that are not factual. This can be effective for tasks such as information retrieval, where constituent claims may be evaluated in isolation for factuality, but is not appropriate for reasoning tasks, as steps of a logical argument can be evaluated for correctness only within the context of the claims that precede them. To capture this, we define "coherent factuality" and develop a conformal-prediction-based method to guarantee coherent factuality for language model outputs. Our approach applies split conformal prediction to subgraphs within a "deducibility" graph" that represents the steps of a reasoning problem. We evaluate our method on mathematical reasoning problems from the MATH and FELM datasets and find that our algorithm consistently produces correct and substantiated orderings of claims, achieving coherent factuality across target coverage levels. Moreover, we achieve 90% factuality on our stricter definition while retaining 80% or more of the original claims, highlighting the utility of our deducibility-graph-guided approach.